#Load the data
nypd_precinct <- read.csv("NYPD_Complaint_Data_Current__Year_To_Date_.csv")
nypd<-read.csv("NYPD_Complaint_Data_Current__Year_To_Date - filtered.csv")
nypd$CMPLNT_FR_DT <- mdy(nypd$CMPLNT_FR_DT)
nypd$CMPLNT_FR_TM <- format(as.POSIXct(nypd$CMPLNT_FR_TM, format = "%H:%M:%S"), "%H")
nypd$CMPLNT_FR_YR <- format(as.POSIXct(nypd$CMPLNT_FR_DT, format = "%Y-%M-%D"), "%Y")
nypd$CMPLNT_FR_YRMT<-format(nypd$CMPLNT_FR_DT, "%y-%m")
nypd<-nypd%>%
filter(CMPLNT_FR_YR <= 2021)
plot_data<-nypd %>%
filter(CRM_ATPT_CPTD_CD == 'COMPLETED')%>%
filter(VIC_SEX == "F"|VIC_SEX=="M")%>%
select(CMPLNT_FR_TM,VIC_SEX,CMPLNT_NUM) %>%
group_by(CMPLNT_FR_TM,VIC_SEX) %>%
count(CMPLNT_NUM)%>%
group_by(CMPLNT_FR_TM,VIC_SEX) %>%
summarise(Victum_num = sum(n))%>%
arrange(VIC_SEX,CMPLNT_FR_TM)
## `summarise()` has grouped output by 'CMPLNT_FR_TM'. You can override using the
## `.groups` argument.
plot1<-plot_data %>%
ggplot(.,aes(CMPLNT_FR_TM,Victum_num))+
theme_bw()+
geom_point(aes(color=VIC_SEX))+
scale_shape_discrete(guide=FALSE)+
labs(x="Hours", y="Total number of victims", title="Total number of victims across 24 hours")+
theme(plot.title=element_text(hjust=0.5))
interactiveplot1<-ggplotly(plot1) %>%
layout(legend=list(orientation="h", x=0.2, y=-0.2), hovermode="x")
## Warning: It is deprecated to specify `guide = FALSE` to remove a guide. Please
## use `guide = "none"` instead.
interactiveplot1
plot_data2<-nypd %>%
filter(CRM_ATPT_CPTD_CD == 'COMPLETED')%>%
filter(SUSP_RACE !="" )%>%
filter(CMPLNT_FR_YR != 2021&CMPLNT_FR_YR != 2020)%>%
mutate(SUSP_RACE=case_when(SUSP_RACE=="BLACK"~"BLACK",
SUSP_RACE=="BLACK HISPANIC"~"BLACK",
SUSP_RACE=="WHITE"~"WHITE",
SUSP_RACE=="WHITE HISPANIC"~"WHITE",
TRUE ~ "OTHER"))%>%
select(CMPLNT_FR_YR,SUSP_RACE,CMPLNT_NUM) %>%
group_by(CMPLNT_FR_YR,SUSP_RACE) %>%
count(CMPLNT_NUM)%>%
group_by(CMPLNT_FR_YR,SUSP_RACE) %>%
summarise(SUSP_num = sum(n))%>%
arrange(CMPLNT_FR_YR,SUSP_RACE)
## `summarise()` has grouped output by 'CMPLNT_FR_YR'. You can override using the
## `.groups` argument.
fig <- plot_ly(plot_data2, x = ~CMPLNT_FR_YR, y = ~SUSP_num, type = 'scatter', mode = '', color = ~SUSP_RACE)
fig <- fig%>%layout(title = 'Total number of suspects each year',
xaxis = list(title = 'Year'),
yaxis = list (title = 'Total number of suspects'))
fig
plot_data3<-nypd%>%
filter(nypd$CMPLNT_FR_YR == 2021)%>%
filter(BORO_NM!="")%>%
select(CMPLNT_FR_YRMT,BORO_NM,CMPLNT_NUM) %>%
group_by(CMPLNT_FR_YRMT,BORO_NM) %>%
count(CMPLNT_NUM)%>%
group_by(CMPLNT_FR_YRMT,BORO_NM) %>%
summarise(CMPLNT_num = sum(n))%>%
arrange(CMPLNT_FR_YRMT,BORO_NM)
## `summarise()` has grouped output by 'CMPLNT_FR_YRMT'. You can override using the
## `.groups` argument.
plot3<-plot_ly(plot_data3,x = ~CMPLNT_num, y = ~reorder(BORO_NM, (CMPLNT_num)), type = 'bar',
name = ~CMPLNT_FR_YRMT, color = ~CMPLNT_FR_YRMT) %>%
layout(yaxis = list(title = 'Count'), barmode = 'stack')
plot3 <- plot3%>%layout(title = 'Total number of crimes of each borough in 2021',
xaxis = list(title = 'Name of Borough'),
yaxis = list (title = 'Total number of crimes'))
plot3
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors
nypd %>%
group_by(BORO_NM, LAW_CAT_CD) %>%
summarize(count = n()) %>%
ggplot(aes(x=count, y=reorder(BORO_NM, -(count)), fill=LAW_CAT_CD)) +
geom_bar(stat="identity") +
coord_flip() +
ggtitle("Number of Crime by Borough and its Crime Type") +
xlab("Percent") + ylab("Name of Borough")
## `summarise()` has grouped output by 'BORO_NM'. You can override using the
## `.groups` argument.
nypd$day_by_day_in_a_week<- wday(nypd$CMPLNT_FR_DT, label=TRUE)
return_by_hour <- function(x) {
return (as.numeric(strsplit(x,":")[[1]][1]))
}
nypd_by_hour <- nypd %>%
mutate(Hour = sapply(CMPLNT_FR_TM, return_by_hour)) %>%
group_by(day_by_day_in_a_week, Hour) %>%
summarize(count = n())
## `summarise()` has grouped output by 'day_by_day_in_a_week'. You can override
## using the `.groups` argument.
nypd_by_hour$day_by_day_in_a_week <- factor(nypd_by_hour$day_by_day_in_a_week, level = c("Sun","Mon","Tue","Wed","Thu","Fri","Sat"))
nypd_by_hour$Hour <- factor(nypd_by_hour$Hour, level = 0:23, label = c(0:23))
nypd_by_hour %>%
ggplot(aes(x = Hour, y = day_by_day_in_a_week, fill = count)) + geom_tile() +
scale_fill_continuous(trans = 'reverse') + ggtitle("Number of Crime reported by Type")
data<-nypd_precinct%>% filter(CRM_ATPT_CPTD_CD !="" )
data <- data %>% group_by(ADDR_PCT_CD)%>%
count(CRM_ATPT_CPTD_CD)
data1 <-data[which(data$CRM_ATPT_CPTD_CD == "ATTEMPTED"),]
data_attempted <-select(data1, c('ADDR_PCT_CD','n'))
names(data_attempted)[1] <- 'police_precinct'
names(data_attempted)[2] <-'attempted'
data2 <-data[which(data$CRM_ATPT_CPTD_CD == "COMPLETED"),]
data_completed <-select(data2, c('ADDR_PCT_CD','n'))
names(data_completed)[1] <- 'police_precinct'
names(data_completed)[2] <-'completed'
data_total <- merge(x=data_attempted, y=data_completed, by= "police_precinct")
data_total$total_crime <- data_total$attempted + data_total$completed
datajson <- geojsonio::geojson_read("https://data.beta.nyc/dataset/5ed20732-5cf9-4812-b8ac-70ad4d10a1ca/resource/375dcf37-5cd9-4c74-9c53-c638b6bb62d0/download/742720184001424d85664732f950040apoliceprecincts.geojson", what = "sp")
bins <- c(0, 2000, 4000, 6000, 8000, 10000, 12000, Inf)
pal <- colorBin("YlOrRd", domain = data_total$total_crime, bins = bins)
leaflet(datajson) %>%
addProviderTiles("MapBox", options = providerTileOptions(
id = "mapbox.light",
accessToken = Sys.getenv('MAPBOX_ACCESS_TOKEN')))%>%
addProviderTiles("Stamen.TonerLite") %>%
addPolygons(
fillColor = ~pal(data_total$total_crime),
weight = 2,
opacity = 1,
color = "white",
dashArray = "3",
fillOpacity = 0.7,
highlightOptions = highlightOptions(
weight = 5,
color = "#666",
dashArray = "",
fillOpacity = 0.7,
bringToFront = TRUE),
label=paste('Number of Total Crime:', data_total$total_crime,
'; Number of Completed Crime:',data_total$completed,
'; Number of Attempted Crime:',data_total$attempted,
'; Police Precinct:',data_total$police_precinct)
)
nypd <- nypd %>% slice_sample(n = 100)
pal = colorFactor("Set1", domain = nypd$LAW_CAT_CD)
color = pal(nypd$LAW_CAT_CD)
popup_info <- paste("Status of Crime:",nypd$CRM_ATPT_CPTD_CD,"<br/>",
"Specific location of occurrence:",nypd$LOC_OF_OCCUR_DESC,"<br/>",
"Patrol Borough:",nypd$PATROL_BORO,"<br/>")
leaflet(nypd) %>%
addProviderTiles("Stamen.TonerLite") %>% #<<
addCircles(col=color,popup = popup_info)%>%
addLegend(pal = pal,values = nypd$LAW_CAT_CD, title = "Level of Offense")
## Assuming "Longitude" and "Latitude" are longitude and latitude, respectively